@pmichel31415 pmichel31415 released this Sep 18, 2018 · 82 commits to master since this release

Assets 2

DyNet v. 2.1 incorporates the following changes:

Link to the 2.1 documentation: https://dynet.readthedocs.io/en/2.1/

@neubig neubig released this Feb 16, 2018 · 186 commits to master since this release

Assets 2

DyNet v. 2.0.3 incorporates the following changes:

  • On-GPU random number generation (#1059 #1094 #1154)
  • Memory savings through in-place operations (#1103)
  • More efficient inputTensor that doesn't switch memory layout (#1143)
  • More stable sigmoid (#1200)
  • Fix bug in weight decay (#1201)
  • Many other fixes, etc.

Link to the documentation: Dynet v2.0.3

@neubig neubig released this Dec 21, 2017 · 234 commits to master since this release

Assets 2

v 2.0.2 of DyNet includes the following improvements. Thanks to everyone who made them happen!

Done:

Better organized examples: #191
Full multi-device support: #952
Broadcasting standard elementwise operations: #776
Some refactoring: #522
Better profiling: #1088
Fix performance regression on autobatching: #974
Pre-compiled pip binaries
A bunch of other small functionality additions and bug fixes

@neubig neubig released this Sep 2, 2017 · 431 commits to master since this release

Assets 2

DyNet v2.0.1 made the following major improvements:

Simplified training interface: #695
Support for multi-device computation (thanks @xunzhang !): #704
A memory efficient version of LSTMBuilder (thanks @msperber): #729
Scratch memory for better memory efficiency (thanks @zhisbug @Abasyoni !): #692
Work towards pre-compiled pip files (thanks @danielhers !)

@neubig neubig released this Jul 10, 2017 · 607 commits to master since this release

Assets 2

This release includes a number of new features that are breaking changes with respect to v1.1.

  • DyNet no longer requires boost (thanks @xunzhang)! This means that models are now not saved in Boost format, but instead a format supported natively by DyNet.
  • Other changes to reading and writing include the ability to read/write only parts of models. There have been a number of changes to the reading/writing interface as well, and examples of how to use it can be found in the "examples". (#84)
  • Renaming of "Model" as "ParameterCollection"
  • Removing the dynet::expr namespace in C++ (now expressions are in the dynet:: namespace)
  • Making VanillaLSTMBuilder the default LSTM interface #474

Other new features include

@neubig neubig released this Jun 28, 2017 · 822 commits to master since this release

Assets 2

This is the branch before transitioning to version 2.

Assets 2

This is the first release candidate for DyNet version 1.0.
Compared to the previous cnn, it supports a number of new features:

  • Full GPU support
  • Simple support of mini-batching
  • Better integration with Python bindings
  • Better efficiency
  • Correct implementation of l2 regularization
  • More supported functions
  • And much more!